Search

Objective·To develop a machine learning approach for early identification of metabolic syndromes associated with inflammatory metabolic state changes in breast cancer patients after neoadjuvant therapy, using common laboratory and transthoracic echocardiography indices.Methods·Female patients with primary invasive breast cancer diagnosed at the Department of Breast Surgery, Renji Hospital, Shanghai Jiao Tong University School of Medicine, between September 2020 and September 2022, were included. General patient information, laboratory test results, and transthoracic echocardiography data were collected. After feature extraction, five machine learning algorithms, including random forest (RF), gradient boosting (GB), support vector machine (SVM), K-nearest neighbor (KNN), and decision tree (DT), were applied to construct a prediction model for the changes of the patients′ metabolic state after neoadjuvant therapy, and the prediction performances of the five models were compared.Results·A total of 232 cases with valid clinical data were included, comprising 135 cases before neoadjuvant therapy and 97 cases after completing 4 cycles of neoadjuvant therapy. Feature extraction identified five key features: white blood cell count, hemoglobin, high-density lipoprotein (HDL), interleukin-2 receptor, and interleukin-8. In the multi-feature analysis, the area under the receiver operating characferistic curve (AUC) was higher in the combination of white blood cell count, hemoglobin and HDL compared to the combination of interleukin-2 receptor and interleukin-8 (RF: 0.928 vs 0.772, GB: 0.900 vs 0.792, SVM: 0.941 vs 0.764, KNN: 0.907 vs 0.762, DT: 0.799 vs 0.714). The RF, SVM, and GB models showed higher AUC (0.928, 0.941, 0.900) and accuracy (0.914, 0.897, 0.776). The SVM model exhibited superior accuracy in the training data compared to the RF and GB models (P=0.394, 0.122 and 0.097, respectively).Conclusion·The SVM model can be used to establish a prediction model for identifying breast cancer patients at high risk of developing inflammatory metabolic state-related metabolic syndrome after neoadjuvant therapy by incorporating five common clinical indicators, namely, white blood cell count, hemoglobin, high-density lipoprotein, interleukin-2 receptor, and interleukin-8. SVM modeling may be useful for clinicians to establish individualized screening protocols based on a patient′s inflammatory metabolic state.

(1) Background: The benefits of weight management are widely recognized, and prolonged fasting duration has become a common method for weight control. The suitability of time-restricted eating (TRE) for elderly individuals remains controversial. This study aims to examine the correlation between fasting duration and mortality within a nationally representative cohort of elderly individuals in the United States. (2) Methods: Data were extracted from a prospective cohort study conducted as part of the National Health and Nutrition Examination Survey (NHANES) from 2005 to 2018. Participants aged over 60 with complete data on dietary intake and mortality follow-up information were included. Fasting duration was assessed using two 24 h dietary recalls. All the participants were categorized into fasting duration quartiles. Mortality outcomes were ascertained through the National Death Index. Cox proportional hazards regression models were utilized to analyze the association between fasting duration and mortality. (3) Results: The final analysis included 10,561 elderly participants (mean age 69.89, 45.58% male). Individuals with the longest fasting duration (over 12.38 h) had a significantly higher risk of CVD mortality compared to those with a normal fasting duration (10.58-12.38 h). This elevated CVD mortality risk was particularly pronounced in males, individuals over 70 years old, and non-shift workers. A non-linear relationship was observed between fasting duration and all-cause mortality and CVD mortality. (4) Conclusions: Prolonged fasting periods are associated with a higher risk of CVD mortality in the elderly population, although this correlation is not evident for all-cause, cancer, or other-cause mortality. A fasting duration of 11.49 h correlates with the lowest mortality risk. Additionally, elderly individuals with the shortest fasting duration exhibit elevated hazard ratios for both cancer and other-cause mortality. As with any health intervention, clinicians should exercise caution when recommending a fasting regimen that is personalized to the health condition of people who are older. Further research through randomized controlled trials should be conducted to comprehensively investigate the impact of TRE on mortality.